RSSAmplifier

Blog

Nilesh's Blog

I'm an engineer passionate about tackling challenges and contributing to open source projects. In my free time, I love diving into books fiction, science, tech and human behavior

nilesh-agarwal.comRSS feed ↗10 posts

Latest posts

Making AI Argue With Itself

I've been running background agents overnight, queuing up a list of tasks before bed, and waking up to pull requests in the morning. The code works. But then I spent half the next day arguing with the agent about edge cases, error handling, and structural decisions it made

Building the harness for RL Coding Agents

Today's AI coding agents can generate impressive volumes of code in a single pass, spinning up entire modules, scaffolding full applications, and writing hundreds of lines in one go. But there's a gap between generating code and shipping code. The output of these long-running sessions is

High-Performance Model Weight Storage and Distribution in Cloud Environments

With the rapid scaling of AI deployments, efficiently storing and distributing model weights across distributed infrastructure has become a critical bottleneck. Here's my analysis of storage solutions optimized specifically for model serving workloads. The Challenge: Speed at Scale Model weights need to be loaded quickly during initialization and

Three-Tier Storage Architecture for Fast LLM Inference in the Cloud

Large Language Model (LLM) inference workloads deal with extremely large model files (often many gigabytes) that must be loaded quickly and repeatedly across distributed GPU instances. Traditional single-tier storage (either solely local disk or only remote cloud storage) cannot meet the throughput and latency demands of serving these models at

AI-Assisted “Vibe” Coding - For Work / Play

I began exploring vibecoding for both my personal projects and Inferless, and I experienced firsthand how it enhanced both. In technical terms "Vibe" coding is an AI-assisted software development approach where you describe the desired functionality in natural language, and AI tools generate the corresponding code. After several

Superintelligence: Paths, Dangers, Strategies

Drawing on general ideas popularized by Nick Bostrom’s Superintelligence , as well as broader AI discussions—and an outline of how such an intelligence might come about and “take off.” What Is Superintelligence? Definition A superintelligence is typically defined as any intellect or system that greatly

Hitchhikers Guide To Galaxy

Insignificance of Problems : The book opens with Arthur Dent desperately trying to stop a bulldozer from demolishing his house. Moments later, Earth itself is destroyed to make way for an intergalactic highway. This stark juxtaposition humorously reminds us how easily we can become consumed by seemingly urgent problems that are

2024 Wrapped

If I had to sum up 2024 in two words, they'd be "adventure" and "change." The year kicked off with the biggest change of all—moving to the US and settling in San Francisco. It was a thrilling yet challenging transition. I quickly

Streaming with Nvidia Triton

Making bits move faster